INDEX

Explanations

instances where something reminds the viewer of something else

oai_token-act-pair · gpt-3.5-turbo

instances of the word "remind" and its variations, indicating references to memories or associations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

estern

-0.90

 ILCS

-0.73

adesh

-0.62

ccording

-0.61

á

-0.60

 deductible

-0.59

inals

-0.59

INA

-0.59

bard

-0.58

DT

-0.58

POSITIVE LOGITS

ingly

1.03

ĸļ

0.97

us

0.82

fulness

0.81

 remind

0.81

 vigilance

0.77

akeru

0.75

 reminded

0.72

remember

0.71

stru

0.70

Activations Density 0.011%

instances where something reminds the viewer of something else

instances of the word "remind" and its variations, indicating references to memories or associations

No Comments

No Known Activations